Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.

Technology for placing a user on-hold can include sending a push notification to a user device after the call has been placed on-hold. A link in the push notification can request authentication credentials from the user. When the authentication credentials have been received and verified, a chat window can be launched via an application on the user device. The intent of the call can be determined based at least in part by information received via the chat window. The authentication information and the intent of the call can be transferred to a representative answering the call.

Technology for placing a user on-hold can include sending a push notification to a user device after the call has been placed on-hold. A link in the push notification can request authentication credentials from the user. When the authentication credentials have been received and verified, a chat window can be launched via an application on the user device. The intent of the call can be determined based at least in part by information received via the chat window. The authentication information and the intent of the call can be transferred to a representative answering the call.

An apparatus is disclosed. For example, the apparatus includes a first communication interface to establish a first communication path with a first endpoint device, a second communication interface to establish a second communication path with a second endpoint device, wherein the second endpoint device is to establish a voice call with the first endpoint device, a processor, and a non-transitory computer-readable medium storing a plurality of instructions. The instructions when executed by the processor cause the processor to detect a request to transfer the second communication path from the second endpoint device to a third endpoint device, wherein the request includes information obtained by the third endpoint device via near field communications (NFC) with the second endpoint device and transfer the second communication path from the second endpoint device to the third endpoint device to disconnect the second endpoint device.

Techniques for determining a global state for multiple related calls are disclosed. A first call between a first device and a second device is established, where the first call is assigned a user call identifier. A second call between the first device and a third device is established. A shared call operation is established by assigning the user call identifier to the second call. The user call identifier is assigned to the second call in addition to already being assigned to the first call. A first status of the first call and a second status of the second call are determined. The first status and the second status are used to determine a global state of the shared call operation. The global state of the shared call operation is updated in response to one or both of the first status or the second status changing.

A determination is made that a real-time communication session (e.g., a voice call) between a first agent terminal and a customer communication endpoint has been placed on hold by a first contact center agent. An estimated hold time for the real-time communication is determined, based on a rule, in response to determining that the real-time communication session has been placed on hold. It is determined that the estimated hold time for the real-time communication session has expired. In response to determining that the estimated hold time for the real-time communication session has expired, one or more actions occur. For example, the real-time communication session is automatically transferred to a second agent terminal.

One example may include receiving a message with call data for a future call between a calling party and a called party, identifying a profile identifier from the call data identifying an enhanced call information profile associated with the calling party, and creating a call message header with a code object having the enhanced call information to include with a call message when placing the future call.

One example may include identifying a header of a call message includes enhanced call data, identifying a code object from the call header identifying textual information and one or more images to display during a call connection, displaying the textual information and the one or more images identified from the code object on a mobile device, and connecting a call to the mobile device.

One example may include identifying a header of a call message includes enhanced call data, identifying a code object from the call header identifying textual information and one or more images to display during a call connection, displaying the textual information and the one or more images identified from the code object on a mobile device, and connecting a call to the mobile device.

Implementations are directed to using an assistant to initiate automated telephone calls with entities. Some implementations identify an item of interest, identify a group of entities associated with the item, and initiate the calls with the entities. During a given call with a given entity, the assistant can request a status update regarding the item, and determine a temporal delay before initiating another call with the given entity to request a further status update regarding the item based on information received responsive to the request. Other implementations receive a request to perform an action on behalf of a user, identify a group of entities that can perform the action, and initiate a given call with a given entity. During the given call, the assistant can initiate an additional call with an additional entity, and generate notification(s), for the user, based on result(s) of the given call and/or the additional call.