Abstract:
Contact centers continually monitor the performance of their resources (e.g., human and automated agents) used for processing work items. An agent with a primary skill receives a flow of work items each having an attribute associated with that particular primary skill. However, agents often have non-primary skills and may serve as a backup for other agents. Measuring the agent's skill level with respect to a non-primary skill allows agents to be scored and potentially identified as having the skill as a primary skill. Selectively providing agents with non-primary work items and monitoring the agent's performance with those work items provides a means to assess an agent's non-primary skill using real work items and without the need for testing resources.
Abstract:
A contact center, methods, and mechanisms are provided for dynamically assembling a team of resources to handle a work item. The work item is analyzed for any needs and a suitable team of resources is selected based at least partially on those needs. Each of the resources can be reserved and applied to a work item for a duration of time that the work item is being handled. As the workflow associated with the work item progresses, the needs of the work item are reevaluated for any changes that may require a modification to the team of resources. When the changes require modification, the team of resources can be adjusted on the fly to suit the changing needs of the work item.
Abstract:
A geo-spatial grammar comprises rules, syntax, and other means by which a data input is determined to have a meaning associated with a particular event. The event may then be provided to an application, such as a calendaring or messaging application. As a benefit, an input, such as a user speaking the phrase, “I'll be there in an hour,” may be interpreted, via the geo-spatial grammar, as an event (e.g., “I'll be in the office,” “I'll join you for dinner,” “I'll be home,” etc.). An application may then perform an action based upon the event (e.g., reschedule the meeting that starts in five minutes, present directions to the restaurant on the user's car's navigation system, notify the user's spouse, etc.).
Abstract:
Businesses have long appreciated the advantages of anticipating potential customers' needs. Directing marketing activities towards non-customers, persons not having such a need, wastes resources of the business and may damage a business' reputation. By providing a location-based analysis of a user's activities, such as by an opt-in application for a mobile device carried by the user, subject matter relevant and timely information on goods and/or services of the business may be provided to the user.
Abstract:
Contact center agents often work in close proximity to other agents. As a primary agent is engaged in a call, a neighboring agent speech may be picked up by the primary agent's microphone. Contact centers using automated speech recognition systems may monitor the agent's speech for key terms and, if detected, respond accordingly. Determining a primary agent spoke a key term, when the true speaker of the key term is a neighboring agent, may cause errors or other problems. Characterizing at least the primary agent's voice and then, once a key term is detected, determining if it was the primary agent that spoke the key term, may help to reduce the errors. Additionally, computational requirements may be reduced as non-key terms may be quickly discarded and optionally, key terms determined to not have been spoke by the primary agent, may also be discarded without further processing.
Abstract:
Some social networks provide message histories that record information about previous posts that users make to the social media network. From this information, a contact center determines trends in the usage of a social media network by a user. The contact center can mine the message history database for times, frequency of posts, location of the user during posts, and other information provided in the message histories. From this information or metadata about the messages, the contact center develops trends about the user's postings of messages on social media networks. The contact center can further receive subsequent posts and read metadata related to the subsequent posts. The new metadata can be used to modify the trends over time.
Abstract:
A semantic translation model system is described along with various methods and mechanisms for administering the same. The semantic translation model system proposed herein creates an intermediate representation and a knowledge base in multiple languages, reducing the amount of time and expensive resources typically required for translation and automatic response to written communications. The system also removes the problem of a translation being influenced by a person's writing style and human misinterpretation and provides ongoing translation to keep the system current.
Abstract:
A prioritization and time allocation by customer service is provided, whereby the customer service agents are incentivized to accept those tasks which more closely align with the objectives of a call center. Individual agents will then be able to pursue their own methodology to achieve their own goals and, in the process, pursue an objective of the contact center.
Abstract:
A system can determine a best routing of a customer contact based on analysis of one or more automatically generated answers. A customer may provide an inquiry through a social media contact. The contact center can analyze the inquiry to generate one or more automated answers. The system then analyzes the automated answers. The analysis may include studying various attributes of the answer, either in relation to the inquiry or based in historical data. From the analysis, the system can modify the answers and/or provide a different or improved pool of agents to handle the contact. Thus, an improved set of answers and agents is provided for managing the contact.
Abstract:
Methods and systems for identifying specified phrases within audio streams are provided. More particularly, a phrase is specified. An audio stream is them monitored for the phrase. In response to determining that the audio stream contains the phrase, verification from a user that the phrase was in fact included in the audio stream is requested. If such verification is received, the portion of the audio stream including the phrase is recorded. The recorded phrase can then be applied to identify future instances of the phrase in monitored audio streams.