Abstract: Techniques are described herein for predicting one or more behaviors by an email recipient and, more specifically, to machine learning techniques for predicting one or more behaviors of an email recipient, changing one or more components in the email to increase the likelihood of a behavior, and determining and/or scheduling an optimal time to send the email. Some advantages of the embodiments disclosed herein may include, without limitation, the ability to predict the behavior of the email recipient and suggest the characteristics of an email which will increase the likelihood of a positive behavior, such as a reading or responding to the email, visiting a website, calling a sales representative, or opening an email attachment.

Abstract: Techniques are described herein for classifying an electronic message with a particular project from among a plurality of projects. In some embodiments, first and second users associated with the electronic message are identified, and one or more first projects associated with the first user and one and more second projects associated with the second user are determined. Projects that are in common between the first projects and the second projects are determined. When only a single project is in common, the electronic message is associated with the single project. When more than a single project is in common, features associated with each of the projects found to be in common are analyzed by a machine learning model to determine the most likely project to associate with the electronic message from among the projects found to be in common.

Abstract: An apparatus, system, and method are disclosed for generating contact plans and responding to web form inquires using the contact plans.

Abstract: Disclosed herein are systems and methods that provide for maintenance of the status of availability of call-center agents through the use of local arbitration between processes and applications that may interact with more than one resource of telephone contacts between differing activities or work for these call-center agents. Detailed information on various example embodiments of the inventions are provided in the Detailed Description below, and the inventions are defined by the appended claims.

Abstract: A method to analyze and determine which source content and user interactions are most popular is provided. The method generates scores for items, e.g., articles, topics, authors, or influencers, on a particular source based on data gathered from both the particular source and social media sources. The scores are used to rank items of the same type, and determine which items are the most popular. The method may also take demographic information as input. Using the demographic information, the system may determine the popularity of a particular item in a particular demographic. The method may also predict which demographic an item may be the most popular in. Furthermore, the method may give a recommendation on which author should write on a particular topic, which topic is most likely to be the most popular for a particular demographic, and which influencers should promote the article.

Abstract: Techniques are described herein for predicting one or more behaviors by an email recipient and, more specifically, to machine learning techniques for predicting one or more behaviors of an email recipient, changing one or more components in the email to increase the likelihood of a behavior, and determining and/or scheduling an optimal time to send the email. Some advantages of the embodiments disclosed herein may include, without limitation, the ability to predict the behavior of the email recipient and suggest the characteristics of an email which will increase the likelihood of a positive behavior, such as a reading or responding to the email, visiting a website, calling a sales representative, or opening an email attachment.

Abstract: Techniques are described herein for predicting one or more behaviors by an email recipient and, more specifically, to machine learning techniques for predicting one or more behaviors of an email recipient, changing one or more components in the email to increase the likelihood of a behavior, and determining and/or scheduling an optimal time to send the email. Some advantages of the embodiments disclosed herein may include, without limitation, the ability to predict the behavior of the email recipient and suggest the characteristics of an email which will increase the likelihood of a positive behavior, such as a reading or responding to the email, visiting a website, calling a sales representative, or opening an email attachment.

Abstract: Disclosed herein are systems and associated methods for operating web interactive services in conjunction with communication services, linking the communication with the interaction by means of a session-specific identifier such as a telephone number. During the course of a web session, user interaction information may be collected, that information potentially indicating subjects of interest to a user associated with the session-specific identifier. In the event the user uses the identifier make a contact regarding the information, the identifier can be used to associate the interaction information and subjects of interest, such that the contact may have that information and those subjects available to assist a user making contact. Interaction and subject information may also be used to customize the interaction with a contacting user with regard to the routing of a telephone call, a greeting, a product or service offering, or other communication.

Abstract: An apparatus, system, and method are disclosed for generating contact plans and responding to web form inquires using the contact plans.

Abstract: A multiple output relaxation (MOR) machine learning model. In one example embodiment, a method for employing an MOR machine learning model to predict multiple interdependent output components of a multiple output dependency (MOD) output decision may include training a classifier for each of multiple interdependent output components of an MOD output decision to predict the component based on an input and based on all of the other components. The method may also include initializing each possible value for each of the components to a predetermined output value. The method may further include running relaxation iterations on each of the classifiers to update the output value of each possible value for each of the components until a relaxation state reaches an equilibrium or a maximum number of relaxation iterations is reached. The method may also include retrieving an optimal component from each of the classifiers.

Abstract: An apparatus, system, and method are disclosed for providing web-based phone services. Phone calls are initiated by a user control on a web page. A calling module uniquely identifies the telephone call and initiates calling by a dialer. Once the telephone call is established, auxiliary functions such as call monitoring, recording, transfer, or conference calling may be initiated for the call. Additional controls corresponding to the auxiliary functions may provided on the web page or a related web page. The web pages used to provide the user controls may stateless web pages.