A method and apparatus for activity-based users' interests modeling for determining relevance of the content distributed to the users is provided. Modeling of the user's interests starts by collecting information about the actions that the user performed and about the contents that were associated with the actions. That information may be used to determine how much interest the user has had in the individual subjects up to date, and to determine which subjects became more or less important to the user over time. Further processing of the information about the interests of each of the individual users in a group of users may produce characteristics indicating the interests of the group as a whole. Additional processing may generate the information reflecting relative importance of the interests of an individual user in the group to the interests of other users in the same group.

Activity based users' interests modeling for determining content relevance

A set of item-item affinities for a plurality of items is determined based on collaborative-filtering techniques. A set of an item's nearest neighbor items based on the set of item-item affinities is determined. A set of user feature-item affinities for the plurality of items and a set of user features is determined based on least squared regression. A set of a user feature's nearest neighbor items is determined based in part on the set of user feature-item affinities. Compatible affinity weights for nearest neighbor items of each item and each user feature are determined and stored. Based on user features of a particular user and items a particular user has consumed, a set of nearest neighbor items comprising nearest neighbor items for user features of the user and items the user has consumed are identified as a set of candidate items, and affinity scores of candidate items are determined. Based at least in part on the affinity scores, a candidate item from the set of candidate items is recommended to the user.

Determining User Preference of Items Based on User Ratings and User Features

A co-browse service uses JavaScript to allow a web page shown in a user's browser to be viewed remotely. Updates to the web page are rendered into HTML and forwarded on the co-browse session. Aspects of the web page that should not be visible are specified in a list of masked elements which prevents the JavaScript from transmitting the content of those elements on the co-browse session. A person viewing the web page at the remote location can select objects to have those objects highlighted within the user's browser. Likewise the person viewing the web page may manipulate the objects by selecting objects and entering information into the objects. Updates to the web page are collected and aggregated such that only the most recent updates are forwarded on the co-browse session. Updates that don't affect the DOM, such as hover state, are also transmitted on the session.

Integrating co-browsing with other forms of information sharing

Provided are methods, systems and computer program products for providing remote document execution. Such methods, systems and computer program products may include storing an electronic document as a secure electronic file, identifying a signature space in the electronic document, the signature space, after being executed, includes a signature of a signing party of the electronic document, receiving the signature of the signing party into the electronic document stored as the secure electronic file and responsive to receiving the signature of the signing party, converting the electronic document into a read only electronic document.

Systems, methods and computer program products for managing remote execution of transaction documents

Content items are selected to be displayed on a portal page in such a way as to maximize a performance metric such as click-through rate. Problems relating to content selection are addressed, such as changing content pool, variable performance metric, and delay in receiving feedback on an item once the item has been displayed to a user. An adaptation of priority-based schemes for the multi-armed bandit problem are used to project future trends of data. The adaptation introduces experiments concerning a future time period into the calculation, which increases the set of data on which to solve the multi-armed bandit problem. Also, a Bayesian explore/exploit method is formulated as an optimization problem that addresses all of the issues of content item selection for a portal page. This optimization problem is modified by Lagrange relaxation and normal approximation, which allow computation of the optimization problem in real time.

Enhanced matching through explore/exploit schemes

A data source generates a requested page for an electronic network site to include inserted tracking parameters to aid in tracking the activities of the user at the site. The site receives the generated page with the inserted tracking parameters and returns to a user the received page as the requested page with the inserted tracking parameters removed therefrom. The site appends the removed tracking parameters to the URL associated with the returned page at the query string thereof, and sends to a tracking database the appended URL. The tracking database stores the sent URL for being accessed by one or more analytical tools to analyze the tracking parameters regarding the activities of the user at the site.

Systems and methods for tracking user activity at website

Click-to-callback provides an icon or link on a webpage that a user can select or click on. When the icon or link is clicked or otherwise selected, the user is provided with a list of his phone numbers to choose from, or a blank field to enter an alternate number, for an immediate return call from a representative of the entity (e.g., the company) associated with the webpage. When this request is submitted, the representative desirably calls the user back immediately (e.g., within about 10 seconds) to provide assistance. Thus, the user remains on the website, and gets the help he desires to continue on the website, which may, for example, lead to the user making an online purchase.

Systems and methods for click-to-callback

An identification of a customer and identification of a webpage to be transmitted to the customer from a first data system are received Message content is selectively inserted from at least one second data system for the identified customer into the identified webpage The first data system is thereafter notified to transmit the webpage from the first data system to a computer system associated with the identified customer Message content may be generated by the at least one second data system relating to the customer's interaction with the at least one second data system Selective insertion and notification may be achieved by a message system The transmission of the customer/web page identification to the message system and the transmission of the identified web page to the customer may be achieved by the first data system The display of the message content on the web page accessed by the customer via the first data system may notify the customer about the customer's interaction with the at least one second data system

Kevin Anthony Kossow

Papers

Systems and methods for tracking user activity at website

Systems and methods for click-to-callback

Systems and methods for personalized customer messages