Abstract:
A contact center system can receive messages from social media sites or centers. The messages may be in a foreign language. The system can review messages by identifying content in the social media messages with negative/positive sentiment and then identify a seed term in the messages. A seed term can be a word in another language, different from the message body. The seed term is then used to find one or more other words, in the foreign language, that are correlated with the seed term. The identification of the found words in other messages can then be used to determine sentiment in the foreign language.
Abstract:
A method, system, and phonetic search engine are described that enable phonetic searches to have increased relevancy to the searcher. Specifically, phonetic searches on a database containing phonetically-searchable content can have one or more phonetically-confusable terms excluded from search results, thereby leaving search results that more faithfully reflect the search terms used during the phonetic search of the database.
Abstract:
In order to detect a specific codec sequence being used, a signal that is based on a codec sequence is analyzed. The signal is analyzed to determine if there is a pattern in the signal. A pattern of a codec sequence can be a unique pattern of frames, frequencies and/or frequency ranges that are generated based on a specific codec sequence. The pattern is compared to one or more previously stored patterns of codec sequences to see if there is a match. If there is a match, an event is generated. For example, if a known codec sequence that has a poor signal quality is determined to be in use for a voice call, the parties may be notified that the call is likely to be a low quality voice call.
Abstract:
Systems are provided for the automatic analysis of skills in a contact center. More particularly to skills that are available, skills that are requested, and the difference between the two. The system may then determine a number of solutions that, if implemented by the contact center, would allow the contact center to have the skill differential. A decision is then made whereby a factor is utilized to select the more optimal solution from the number of solutions.
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:
Contact centers receive work items for processing by resources, such as human or automated agents. Social media has become a popular medium to receive work items and communicate with customers. Legal concerns, such as those focused on customer privacy, may limit gathering and/or storing of certain customer data on resources controlled by the contact center or require the deletion of data collected from a revoked prior authorization. Storing at least some data, such as a token, within a customer's social media website allows a contact center to maintain connections, transactions, or other information related to a customer or a specific transaction with a customer as long as the customer and/or social media website chose not to delete the token.
Abstract:
Correctly staffing retail settings is a challenge. While calendar based staffing decisions, such as increasing staffing for a holiday sale, may provide high-level staffing recommendations. The activities of customers may be monitored to provide a more granular staffing allocation. Customers who, for example, spend a certain duration of time within one portion of the retail setting may be determined to indicate a need for assistance and a staff member of the retail setting allocated to assist the customer or customers within an area with a spike in customer activity. Similarly, customers who indicate a desire to purchase an item requiring certain staff skills (e.g., verify customer identity, complete legal documents, lift heavy items, etc.) may be detected and an appropriate staff member allocated. As a result, the customer may receive assistance from staff members having the required skills to complete their purchase.
Abstract:
Automated kiosks are often provided in retail settings to provide a convenient and cost-effective means to assist customers of the retail setting and as an alternative or supplement to human agents. Kiosks may work well for certain customers and actions, however, the customer and/or kiosk may fail to effectively interact with each other and leave the customer dissatisfied with the interaction. By determining a meta-meaning associated with a customer's actions with a kiosk, the kiosk may be able to determine whether an agent should be summoned to assist the customer. For example, a customer may be using the kiosk for an unusually long time. In response, an available agent may be notified and approach the customer to offer their assistance; without the customer explicitly requesting such assistance. As a benefit, the retail setting may appear more in-touch with the needs of the customer.
Abstract:
Social media websites occasionally experience a spike in activity known as a viral event or “going viral.” While some viral events are purely entertainment based, such as the latest cat video, other viral events can be specifically relevant to a domain, such as an industry or business. A social media event, such as a common thread of posts, may attract no more than the usual amount of interest or it may be about to “go viral.” As provided herein, social media events may be monitored and evaluated for virality. If an event indicates it will go viral, but has not yet done so, an affected party may be made aware of the event and take steps to curtail negative viral events or to leverage, or even promote, positive viral events.
Abstract:
An automatic timeline and topic normalization mechanism is described along with various methods and systems for administering the same. The temporal correction system proposed herein creates fully interpreted and reordered representations of events within and external to a dialog, reducing the amount of time and expensive resources typically required for reading, comprehension, and response to written communications.