A computer-implemented method for managing calls in a collaboration environment is provided. The method includes receiving, by a processor, a call into a collaboration session of the collaboration environment. The method also includes identifying, by the processor, a user from a plurality of users associated with the collaboration session, based on at least one of contextual information regarding the call and information regarding the plurality of users. The method further includes providing, by the processor, an interface on a device associated with the identified user, wherein the interface enables the identified user to instruct the device to handle the call within the collaboration session.

One example method of operation may include identifying a call from a calling device destined for a mobile device, responsive to identifying a calling device number assigned to the calling device, accessing a call content application programming interface (API), operated by a content delivery device, configured to deliver to the mobile device a first caller identification name (CNAM) or a second CNAM, assigned to the calling device number, determining a context assigned to a mobile device number assigned to the mobile device, selecting one of the first CNAM and the second CNAM based on the context, and assigning the selected CNAM to the call.

Systems and methods are configured for predictive prompt generation for an interaction between a party and an automated prompt system. In various embodiments, metadata is received on the interaction and provided as input to a multi-label predictive model to generate interaction probabilities for a plurality of prompt information data objects. Each probability generated by the predictive model provides a likelihood a particular information data object needs to be provided to the first party during the interaction. Accordingly, one or more of the prompt information data objects are identified based on the probability of each piece found in the one or more prompt information data objects that satisfy a set threshold and one or more notifications are provided so that the automated prompt system provides at least one of the prompt information data objects to the first party during the interaction.

An observation platform comprises a computer system associated with an organization, a first communication device associated with a first user, a second communication device communicatively coupled with the computer system, and a plurality of additional communication devices associated with different users of a plurality of additional users. The computer system communicates with the first and additional communication devices via the second communication device. The computer system receives, via the second communication device, a signal from the first communication device. A characteristic of the signal corresponds to audible source which is a voice of the first user. The computer system derives context information from a speech to text analysis of the characteristic. The context information comprises a query about the organization. The computer system compiles a response to the query and responds based on the compiled response, via the second communication device, to the first communication device about the query.

Embodiments described herein disclose methods and systems for providing selective data access to representatives. In some embodiments, the system can monitor a call between a user and a representative regarding a subject matter. The user can have an associated profile with data, and the data can be locked such that the representative cannot access the data. During the conversation between the representative and the user, the system can continuously convert both parties' speech into text. The system can determine an intent of the call based on the text and unlock a portion of the data about the user based on the determined intent of the call. Only the unlocked portion of the data is displayed to the representative.

A dialogue device of a dialogue system relating to provision of a response to an inquiry from a user terminal includes an input unit that acquires the inquiry from the user terminal, a transmission unit that connects the user terminal and an operator terminal responding to the inquiry in accordance with the inquiry, an output unit that outputs questions for ascertaining details of the inquiry to the user terminal before connection made by the transmission unit, and a determination unit that determines a mode of the questions made by the output unit in accordance with an operating status of the operator terminal that can respond to the inquiry.

Systems and methods for providing called devices with sets of context data associated with communication sessions are disclosed. In one implementation, a method for generating context data associated with a communications session may include receiving, from a calling device at a first subsystem, a request to establish a communications session. The request may include a first identifier associated with the calling device. The method may further include receiving, at a second subsystem, activities data associated with the calling device that transmitted the request to establish the communications session. The activities data may include a second identifier associated with the calling device and may be indicative of device activities of the calling device. In addition, the method includes determining, using the first identifier and the second identifier, that the received activities data is associated with the calling device that transmitted the request to establish the communications session, generating context data associated with the communications session based on the received activities data, generating visual content based on the generated context data, and establishing the communications session in response to receiving, from a user of the called device, an input command to accept the request.

Systems and methods are described for transmitting and receiving a multimedia content to and fro between a caller mobile device and a callee mobile device in which the multimedia content is from the device of the users involved during ring time of a voice call, streaming live and in real time, and not from any third party multimedia storage server. An aspect of the present disclosure also states that the callee can also reply to the caller by transmitting multimedia content to the caller during the ring time of the voice call, streaming live and in real time.

A two-way communication support system supports two-way communication between a second terminal device which receives, from a first terminal device, first state data changed according to the state of a first user present on a side where the first terminal device is arranged and which outputs an image and a voice indicated by the first state data and the first terminal device. The two-way communication support system includes a state identifier and an output controller. The state identifier analyzes second state data changed according to the state of a second user present on a side where the second terminal device is arranged so as to identify the state of the second user. The output controller causes the first terminal device to output analysis information indicating a result of the identification of the state of the second user performed by the state identifier.

Machine learning models may be used during a communications session to process natural language communications and perform actions relating to the communications session. For example, a machine learning model may be used to provide an automated response to a user, to suggest a completion of text being entered by a user, or to provide information about a relevant resource. Machine learning models may rely on machine learning model data that is updated during a communications session as communications are processed by the machine learning model. To improve the performance of a machine learning model when a user leaves a first communications session and enters a second communications session, the machine learning model data may be stored during a first communications session and then retrieved during the second communications session to initialize a machine learning model for the second communications session.