摘要:
The accent of a party to a call is determined from a speech sample of the party and the call is sent for servicing to a call-center agent who has skill in the determined accent, and preferably to an agent who speaks both the determined language and the language of the accent.
摘要:
The present invention provides a more accurate estimate as to time for completion of a call by using estimated time durations of separate phases of the call and by determining what phase a call is currently on. An important feature of the present invention is the use of automated speech processing techniques to estimate where the customer and agent are in their conversation and to gauge the rate of progress of the call.
摘要:
System and method to adjust an automatic speech recognition (ASR) engine, the method including: receiving social network information from a social network; data mining the social network information to extract one or more characteristics; inferring a trend from the extracted one or more characteristics; and adjusting the ASR engine based upon the inferred trend. Embodiments of the method may further include: receiving a speech signal from a user; and recognizing the speech signal by use of the adjusted ASR engine. Further embodiments of the method may further include: producing a list of candidate matching words; and ranking the list of candidate matching words by use of the inferred trend.
摘要:
A server executing a social media identity and discovery application and method are provided that scan social networking sites for communications. The target content is found with content indicators when communications are put on a social networking site. The content is recorded and evaluated. If the identified content is contextually significant, the alias and the private user data are correlated based on events, and a notification of the correlation is sent to an agent or a contact center system. The agent may verify that the identity of a poster has been accurately correlated with a customer record in the database. The agent or the system has the opportunity to respond to the communication, despite the anonymity of the poster on the social networking site.
摘要:
Method to provide SIP session management of a real-time communication to a softphone client in a virtual machine, including: accepting an invitation to join a SIP session; receiving, by a server-based softphone in the SIP session, a real-time communication that is encoded with at least one SIP session aspect; transmitting the real-time communication and the at least one SIP session aspect to a client-based softphone; and using the at least one SIP session aspect for SIP session management.
摘要:
A system can determine the value of a customer that uses social media. An enterprise can provide an identity of a customer, identities of customers, or a profile of one or more customers. The enterprise can also provide one or more criteria in which to base the customer value calculation. The criteria can include the number of friends for a social media site, the number posts the user creates, the number of responses to the user's postings, the tenor of the user's postings, etc. Resources of information, including historic and current activity on social media sites, public resources, and other sources, are examined to provide a score for each criteria. A customer value score may then be generated from the criteria scores. The value score may then be used to modify the interactions of a contact center with the customer.
摘要:
The present invention comprises a method for: (i) receiving information from a caller C1 and indexing the caller C1 into a first group based, at least in part, on the received information, (ii) transmitting to a participant P1, a first message requesting that the participant P1 assist the caller C1 indexed in the first group, (iii) establishing a conference call between the participant P1 and the caller C1 in response to the participant P1 responding to the first message, (iv) transmitting the first message to a participant P2 when the participant P1 does not respond to the first message, (v) establishing a conference call between the participant P2 and the caller C1 in response to the participant P2 responding to the first message, and (vi) connecting the caller C1 with an agent A1 when a response to the first message is not received from the participant P1 and the participant P2.
摘要:
A method comprising receiving, at a call-processing switch, a call from a calling entity in which the calling entity is a natural person and a telecommunications terminal, and, wherein the call received at the call-processing switch comprises (i) the identity of the caller telecommunications terminal, (ii) the identity of the caller, and (iii) the geo-location of the calling entity. Upon receiving the call, the call-processing switch identifies (i) global contextual information, (ii) contextual information at the calling entity, and (iii) contextual information at the call-processing switch, wherein the temporal order and the hierarchical order of menu items in a menu are reconfigured for presentation to the calling entity based on (i) the identity of the caller telecommunications terminal, (ii) the identity of the caller, (iii) the geo-location of the calling entity, (iv) global contextual information, (v) contextual information at the calling entity, and (vi) contextual information at the call-processing switch.
摘要:
A system is disclosed that features a transport vehicle that carries responsive objects in which the objects are equipped to provide state information about their states when queried. The transport vehicle is outfitted with a proxy that represents the responsive objects. The proxy is configured such that it is better able than the responsive objects to receive state query signals from a querying device. The vehicle is also outfitted with I) sensors that detect the responsive objects and ii) sensors that detect state information of the vehicle, in which both sets of sensors provide information to the proxy. The object sensors are able to detect the state of each responsive object or query the object about its state in the same way as the querying device would query those objects in the prior art. The proxy then responds to the query on behalf of the responsive objects.
摘要:
A distributed interactive voice processing system is disclosed that distributes IVR capabilities to one or more agent terminals associated with a call center. One or more agent terminals support the traditional functions of a live agent, as well as additional IVR capabilities to support the functions of a virtual or automated agent A call management system manages the distributed IVR resources by monitoring the availability status of the live and automated IVR agents in the distributed interactive voice processing system and distributing telephone calls and other types of communications to the appropriate agents. The availability status of the automated IVR agents is based on estimated available CPU cycles on the agent terminal A received call is routed to the extension on the agent terminal associated with the selected IVR channel. A VXML process associated with the selected IVR channel obtains the appropriate application software from a central voiceXML application server and executes the VXML page(s) to play the appropriate prompts from the IVR script to the caller and to collect DTMF or speech recognized inputs from the caller The distributed design allows centralized application management while using distributed resources to provide improved IVR availability.