Abstract:
An information retrieval system allows a user to navigate through a plurality of informational items for a desired informational items, and upon selection of an information item, presents other informational items related to the selected informational item. The information retrieval system in accordance with the principles of the present invention maintains a database that defines a relational association between a plurality of informational items in the system. The relational association is based on historical navigational behavior of users of the information retrieval system, and includes a relationship type, which is based on the characteristic similarities between the informational items, and relationship strength, which is based on the historical frequency of any related informational items being selected by a user within the same information retrieval session. When a navigation from one informational item to another information item is detected, the relationship type and the relationship strength of the two informational items are determined and stored in the database. During a subsequent selection of an informational item, any related informational items related to the selected informational item are sorted based on the respective relationship types and relationship strengths, and are provided in a sorted list from which the user can select.
Abstract:
A method and system for use in an information retrieval system that provides related informational items that can be automatically classified and summarized in a hierarchical manner. The system comprises the steps and means for the presentation and analysis of mined data through the application of four distinct processes, namely, feature selection, clustering, classification and summarization (Figure 1). The implementation of each of these techniques is a single process without regard to order. Individual informational items are analyzed, and relevant features extracted (Figure 3). Individual groups of informational items, otherwise known as clusters, are identified, and rules are determined to allow the assignment of informational items to the previously mentioned groups. Descriptive and meaningful titles are then identified for the groups. Various methods of presenting searched information to an end user are also provided. A method of adaptive clustering is also provided.
Abstract:
A method and article for providing search-specific page sets and query-results listings is provided. The method and article provides end-users with customized, search-specific pages upon which to initiate a query. A method is also provided for defining the custom search page and the custom results page without the need for line-by-line computer coding. The present invention provides product and service information to end-users in an initiative format.
Abstract:
A system, method, and computer program product for dynamically adapting selections in an automatic phone support system is described. The invention may integrate a dynamic knowledge base of responses with the menu selections on an automated phone system or other response system to present the most frequently used items earlier in the option list, or otherwise order options and information. Call data may be captured from single callers or historical ensembles of callers. An automatically generated similarity relationship may be used to initialize the system without historical call data, based on textual similarity or other techniques. Prioritization of options provides a more enjoyable, efficient experience for callers without increasing administrative overhead.
Abstract:
A system, method, and computer program product for dynamically adapting selections in an automatic phone support system is described. The invention may integrate a dynamic knowledge base of responses with the menu selections [306] on an automatic phone system or other response system to present the most frequently used items earlier in the option list [308], or otherwise order options [314] and information. Call data may be captured from single callers or historical ensembles of callers. An automatically generated similarity relationship may be used to initialize the system without historical call data, based on textual similarity or other techniques [310]. Prioritization of options [316] provides a more enjoyable, efficient experience for callers without increasing administrative overhead.
Abstract:
A system, method, and computer program product for determining the emotional content of an electronic correspondence (308) to route or prioritize the information (105), to set the expectations of a customer support worker (115, 120, 125, 130), to flag those workers who are using inappropriate language with the customer, or determine another best course to send the correspondence. In a preferred embodiment, a customer sends an electronic correspondence to a company via email. Emotionally charged words or symbols in each sentence are detected (224). The message is then given an emotional ranking (224) which is used to determine what future action is most appropriate for the correspondence.
Abstract:
A system, method, and computer program product for dynamically adapting selections in an automatic phone support system is described. The invention may integrate a dynamic knowledge base of responses with the menu selections [306] on an automatic phone system or other response system to present the most frequently used items earlier in the option list [308], or otherwise order options [314] and information. Call data may be captured from single callers or historical ensembles of callers. An automatically generated similarity relationship may be used to initialize the system without historical call data, based on textual similarity or other techniques [310]. Prioritization of options [316] provides a more enjoyable, efficient experience for callers without increasing administrative overhead.
Abstract:
A system, method, and computer program product for dynamically adapting selections in an automatic phone support system is described. The invention may integrate a dynamic knowledge base of responses with the menu selections [306] on an automatic phone system or other response system to present the most frequently used items earlier in the option list [308], or otherwise order options [314] and information. Call data may be captured from single callers or historical ensembles of callers. An automatically generated similarity relationship may be used to initialize the system without historical call data, based on textual similarity or other techniques [310]. Prioritization of options [316] provides a more enjoyable, efficient experience for callers without increasing administrative overhead.